© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44252
    Prev
    Next
    INDEX
    Explanations

    gender roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ありません
    0.49
    ້ມ
    0.48
    Saw
    0.48
    ться
    0.48
    Mamm
    0.47
    </strong>
    0.47
    Scripts
    0.46
    Aw
    0.46
    subheader
    0.46
    Cher
    0.46
    POSITIVE LOGITS
     varchar
    0.51
     kupu
    0.49
     quels
    0.47
     NGO
    0.46
     Yard
    0.46
     sentencing
    0.46
     교
    0.45
     bandit
    0.45
     propaganda
    0.45
    炕
    0.45
    Activations Density 0.000%

    No Known Activations